What we believe

What we believe

"Here's to the crazy ones. The misfits, the rebels, the troublemakers, the round pegs in the square holes, the ones who see things differently. They're not fond of rules, and they have no respect for the status quo. You can quote them, disagree with them, glorify or vilify them. About the only thing you can't do is ignore them. Because they change things - they push the human race forward. And while some may see them as the crazy ones, we see genius. Because the people who are crazy enough to think they can change the world, are the ones who do." --Steve Jobs

“When something is important enough, you do it even if the odds are not in your favor. ” --Elon Musk

“The best way to predict the future is to create it ” --Abraham Lincoln

CogAI4Sci team

CogAI4Sci team

Our Cognitive AI for Science (CogAI4Sci) team at National University of Singapore focuses on two branches of research: 1) develop AI inspired by cognitive science to enable machine to learn, reason and create. and 2) Use AI to improve biomedical scientific discovery and medical practice

Before starting CogAI4Sci team, Dianbo Liu was a group leader at the Broad Institute of MIT and Harvard. Prior to the Broad Institute, Dianbo worked as a postdoctoral researcher with Prof. Yoshua Bengio (a Turing Award winner) and led the Humanitarian AI team at the Mila-Quebec AI Institute. This followed his fellowship training and studies in medical informatics at Harvard Medical School. Dianbo earned his PhD from the University of Dundee, Scotland, under the supervision of Prof. Timothea Newman. During his doctoral studies,he received the Vest Scholarship from the Massachusetts Institute of Technology (MIT) and was a special graduate student at the MIT Computer Science and Artificial Intelligence Lab. Dianbo also co-founded two start-ups, "GeneTank" and "SecureAILabs," to advance AI applications in biomedical sciences during his training.

Research aims

Research aims

Employ generative AI and self-supervised learning to analyze and comprehend the growing volume and diversity of biomedical data, with the aim of doubling the average life expectancy worldwide

Use inspiration from human creativity, memory and attention to improve generative models and representation learning for scientific research

Develop and deploy practical AI tools for scientific applications, aimed at transforming Singapore into a leading biomedical AI technology export hub in Asia.

Team

Team

Trang Nguyen Ngoc Phuong (From FTP Vitenam, mentee at Mila-Quebec AI institute, with Prof. Yoshua Bengio)

Hongyu He (From Duke Uni, USA. graduate research assistant)

Zarif Ikram (From Bangladesh University of Engineering and Technology. Mentee)

Maab Elrashid (From Sudan. Mentee at Mila-Quebec AI institute, with Prof. Yoshua Bengio)

Ziqing Mai(From Tsinghua University, China. Mentee, co-supervisd with Hang Zhao)

Arian Khorasani (Msc at Mila-Quebec AI institute with Irina Rish)

Taoyong Cui(From Tsinghua University, China. Mentee)

Rushi Shah (From IIT, Jodhpur, India. Mentee)

Mike Zhu(From Mila, PhD student, co-mentored with Prof.Yue Li (main mentor) at McGill)

Zile Yang(From Wuhan University, China. Mentee)

Anhying Bai(From Tsinghua University, China, Mentee)

Sankepally Sainath Reddy (From IIIT-RAIPUR ,India. Mentee at Broad/MIT/Harvard)

Chengbo Li(From UIUC, USA. Mentee at Harvard/Broad)

Mingyuan Yan (From Huadong Normal Uni.,China. Mentee )

Wenhao Zhao (From Beihang Uni.,China. Mentee )

Jiawei Wu (From Huadong Normal Uni.,China. Mentee )

Zheqi Liu(From Tsinghua Uni.,China. Mentee )

Anirudh Prabhakaran (From NIT,India. Mentee )

Yice Fang(From Tsinghua University, China. Mentee)

Bonaventure F. P. Dossou (Mentee at Mila-Quebec AI institute. next: PhD at McGill )

Rulin Shao (Mentee at MIT/Harvard, Next graduent student at CMU/ Amazon, now PhD at UW)

Loïc Kwate Dassi (Mentee at Mila-Quebec AI institute, Next: DeepMind London )

Oussama Boussif, Mentee at Mila. Next: PhD with Yoshua Bengio at Mila )

Li Huang (Mentee at Harvard. Next: PhD at Tsinghua. Now: faculty at Chinese Academy of Medical Sciences & Peking Union Medical College )

James Assiene (Mentee at Mila-Quebec AI institute. Next: DeepMind London )

Tianyi Zhang (Mentee at Harvard. Next: PhD at ASU )

Léna Néhale Ezzine,Mentee at Mila. Next: PhD with Yoshua Bengio at Mila )

Wisdom d'Almeida (Mentee at Mila-Quebec AI institute. Next: researcher at Miscrosoft/PhD at Oxford )

Jiahe Tian (Mentee at Harvard. Next: graduent student at CMU )

Ruobin Tao(Mentee in Boston, now at University of New South Wales, Australia )

Yuhao Qian (Mentee in Boston. Next: Amazon )

Pascal Junior Tikeng Notsawo (Mentee at Mila-Quebec AI institute. Next: PhD at Mila )

Leyu Dai (Mentee at Harvard. Next: PhD at University of North Carolina at Chapel Hill )

Junfeng Zhi (Mentee at Harvard. Next: graduent student at Duke. Now: engineer at Amazon )

Brice Nanda (Mentee at Mila-Quebec AI institute. Next:Msc at Mila )

Yihe Yang (Mentee at Harvard. Next:Msc at CMU )

Zhuang Ma (Mentee at Harvard. Next: graduent student at CMU )

News

News

  • [Nov 2023] Our exploration of generative models for causal discovery of gene networks Swift-DynGFN is accepted at Neurips Generative model for biology workshop. Congratulatiosn to Trang and all co-authors.
  • [Nov 2023] Make our large language model physical reasoning task COAT is available
  • [June. 2023] Our 2-year effort on attention schema will be presented at Neurips InforCog workshop
  • [Apr. 2023] Present our SAF paper at ICLR 2023 at Kigali, Rwanda
Join our team

Join our team

We are always looking for PhD students, postdocs, interns and visiting scholars to join our lab in the following directions:

  • Cognitively inspired generative machine learning models and self-supervised learning
  • Generative machine learning models and self-supervised learning for science, focusing on biomedical scientific discovery
  • Generative machine learning models and self-supervised learning for medical practice
If you are interested, please fill in this form AND send me an email at

dianbo.liu@alumni.harvard.edu

Selected Publications

Selected Publications

Publications

For the most up-to-date list of publications, see my Google Scholar profile.

Causal Inference in Gene Regulatory Networks with GFlowNet: Towards Scalability in Large Systems
Trang Nguyen, Alexander Tong, Kanika Madan, Yoshua Bengio, Dianbo Liu
Arxiv
Attention Schema in Neural Agents
Dianbo Liu , Samuele Bolotta, He Zhu, Yoshua Bengio, Guillaume Dumas
Arxiv
GFlowOut: Dropout with Generative Flow Networks
Dianbo Liu , Moksh Jain, Bonaventure Dossou, Qianli Shen, Salem Lahlou, Anirudh Goyal, Nikolay Malkin, Chris Emezue, Dinghuai Zhang, Nadhir Hassen, Xu Ji, Kenji Kawaguchi, Yoshua Bengio
ICML 2023
Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
Dianbo Liu, Vedant Shah,Oussama Boussif, Anirudh Goyal, Michael Curtis Mozer,Nicolas Heessm Yoshua Bengio.
ICLR 2023
Construction of extra-large scale screening tools for risks of severe mental illnesses using real world healthcare data
Dianbo Liu , Karmel W Choi, Paulo Lizano, William Yuan, Kun-Hsing Yu, Jordan Smoller, Isaac Kohane
Arxiv
Machine learning approaches to predicting no-shows in pediatric medical appointment
Dianbo Liu, Won-Yong Shin, Eli Sprecher, Kathleen Conroy, Omar Santiago, Gal Wachtel, Mauricio Santillana
NPJ digital medicine 2022
Graph-Based Active Machine Learning Method for Diverse and Novel Antimicrobial Peptides Generation and Selection
Bonaventure F. P. Dossou, Dianbo Liu, Xu Ji, Moksh Jain, Almer M. van der Sloot, Roger Palou, Michael Tyers, Yoshua Bengio
Preprinted
Discrete- Valued Neural Communication
Dianbo Liu, Alex Lamb, Kenji Kawaguchi, Anirudh Goyal, Chen Sun, Michael Curtis Mozer, Yoshua Bengio
Neurips 2021
FeARH: Federated machine learning with anonymous random hybridization on electronic medical records
Jianfei Cui, He Zhu, Hao Deng, Ziwei Chen,Dianbo Liu
Journal of Biomedical Informatics 2021
ENCODE Phase III: Building an Encyclopedia of Candidate cis-Regulatory Elements for Human and Mouse
Jill Moore1, Michael J. Purcaro , Bradley E. Bernstein. . . Dianbo Liu. . . .. Barbara Wold, Ross C. Hardison , al.
Nature 2020
Patients with cancer appear more vulnerable to SARS-COV-2: a multicenter study during the COVID-19 outbreak
(co-first author) Dai, Mengyuan*, Dianbo Liu*, Miao Liu, Fuxiang Zhou, Guiling Li, Zhen Chen, Zhian Zhang et al.
Cancer discovery 2020
Integrative construction of regulatory region networks in 127 human reference epigenomes by matrix factorization
Dianbo Liu, Jose Davila-Velderrain, Zhizhuo Zhang, Manolis Kellis al.
Nucleic acids research 2019
Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records
Li Huang, Andrew L Shea, Huining Qian, Aditya Masurkar, Hao Deng, Dianbo Liu
Journal of biomedical informatics 2019
Get in Touch

Contact

Mila - Quebec AI Institute
6666 St-Urbain, #200
Montreal, QC, H2S 3H1